Journal
NEURAL COMPUTING & APPLICATIONS
Volume 26, Issue 2, Pages 383-390Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-014-1730-x
Keywords
Feedforward neural networks; Gradient method; l(0) Regularization; Sparsity; Convergence
Categories
Funding
- National Natural Science Foundation of China [61101228]
- China Postdoctoral Science Foundation [2012M520623]
Ask authors/readers for more resources
This paper considers the batch gradient method with the smoothing regularization (BGSL0) for training and pruning feedforward neural networks. We show why BGSL0 can produce sparse weights, which are crucial for pruning networks. We prove both the weak convergence and strong convergence of BGSL0 under mild conditions. The decreasing monotonicity of the error functions during the training process is also obtained. Two examples are given to substantiate the theoretical analysis and to show the better sparsity of BGSL0 than three typical regularization methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available